[go: up one dir, main page]

WO2019082993A1 - Système de traitement d'image médicale, système d'endoscope, dispositif d'aide au diagnostic, et dispositif d'aide à la pratique médicale - Google Patents

Système de traitement d'image médicale, système d'endoscope, dispositif d'aide au diagnostic, et dispositif d'aide à la pratique médicale

Info

Publication number
WO2019082993A1
WO2019082993A1 PCT/JP2018/039771 JP2018039771W WO2019082993A1 WO 2019082993 A1 WO2019082993 A1 WO 2019082993A1 JP 2018039771 W JP2018039771 W JP 2018039771W WO 2019082993 A1 WO2019082993 A1 WO 2019082993A1
Authority
WO
WIPO (PCT)
Prior art keywords
light
medical image
area
unit
interest
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/JP2018/039771
Other languages
English (en)
Japanese (ja)
Inventor
林　伸治
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Fujifilm Corp
Original Assignee
Fujifilm Corp
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Fujifilm Corp filed Critical Fujifilm Corp
Priority to JP2019550301A priority Critical patent/JP6850358B2/ja
Publication of WO2019082993A1 publication Critical patent/WO2019082993A1/fr
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B1/00—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor
    • A61B1/04—Instruments for performing medical examinations of the interior of cavities or tubes of the body by visual or photographical inspection, e.g. endoscopes; Illuminating arrangements therefor combined with photographic or television appliances
    • A61B1/045—Control thereof
    • G—PHYSICS
    • G02—OPTICS
    • G02B—OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
    • G02B23/00—Telescopes, e.g. binoculars; Periscopes; Instruments for viewing the inside of hollow bodies; Viewfinders; Optical aiming or sighting devices
    • G02B23/24—Instruments or systems for viewing the inside of hollow bodies, e.g. fibrescopes

Definitions

  • the present invention relates to a medical image processing system that detects a region of interest from medical images, an endoscope system, a diagnosis support device, and a medical service support device.
  • diagnosis support information regarding a pathological condition is obtained by detecting a notable area of interest in a lesion from a medical image and performing image analysis on the detected area of attention. .
  • the acquired diagnostic support information is provided to the user by displaying it on a display unit such as a monitor.
  • the detection level of the region of interest is set to a low level in order to avoid missing of a lesion. Therefore, although it becomes possible to detect a lesioned part with certainty, in many cases, a region such as a normal region that should not be detected as a region of interest is also often detected. That is, there may occur an erroneous detection area which is erroneously detected as an attention area.
  • the present invention relates to a medical image processing system, an endoscope system, a diagnosis support apparatus, and a medical device, which allow a user operating an endoscope to directly make a judgment on each region of interest when detecting a plurality of regions of interest. It aims at providing a work support device.
  • a medical image processing system includes an image acquisition unit, an attention area detection unit, a display unit, a sight line detection unit, and an attention area tip.
  • the image acquisition unit acquires a medical image obtained by imaging an observation target.
  • the attention area detection unit performs an area detection process of detecting the attention area from the medical image.
  • the display unit displays a region of interest in the medical image.
  • the region-of-interest selection unit performs region selection processing for selecting a first region of interest including a line-of-sight point indicating a position at which the line of sight directed by the user to the display unit intersects the display unit.
  • the region selection process it is determined that the first region of interest is an appropriate region correctly detected as the region of interest, and a second region of interest other than the first region of interest among the plurality of regions of interest It is preferable to provide an area determination unit that performs an area determination process that determines that the area is an erroneously detected area erroneously detected as an attention area.
  • the system includes a learning data generation unit that generates learning data for causing the attention area detection unit to be associated by associating the medical image with the determination result of the area determination processing, and the attention area detection unit performs area detection processing or learning It is preferable to use the learning data to perform any of the learning processes for increasing the detection accuracy of the region of interest.
  • Use the learning data generator to associate the medical image with the judgment result of the area judgment processing to generate the learning data to train the attention area detector, and use the learning data to raise the detection accuracy of the attention area
  • the image processing apparatus further includes a specific processing unit to which a learning process is performed, and the attention area detection unit be replaced with the specific processing unit when the learning process is performed.
  • An area selection operation unit that receives a user's operation regarding selection of an attention area is provided, and the attention area selection unit selects an attention area including a gaze point at a timing when the area selection operation unit is operated as a first attention area.
  • the observation time measurement unit measures an observation time as a time during which the gaze point enters the attention area, and the attention area selection unit selects an attention area whose observation time exceeds a specific observation time as a first attention area. Is preferred.
  • the medical image is preferably a normal light image obtained by irradiating light of a plurality of wavelength bands as light of a white band or light of a white band.
  • the medical image is a special light image obtained by irradiating light of a specific wavelength band, and light of the specific wavelength band is preferably a band narrower than the white band.
  • the specific wavelength band includes a wavelength band of 390 nm to 450 nm, or 530 nm to 550 nm, and light of a specific wavelength band has a peak wavelength within the wavelength band of 390 nm to 450 nm, or 530 nm to 550 nm. Is preferred.
  • the specific wavelength band is preferably included in the red band in the visible range.
  • the specific wavelength band includes a wavelength band of 585 nm to 615 nm, or 610 nm to 730 nm, and light of the specific wavelength band has a peak wavelength within the wavelength band of 585 nm to 615 nm, or 610 nm to 730 nm. It is preferable to have.
  • the specific wavelength band includes wavelength bands having different absorption coefficients for oxyhemoglobin and reduced hemoglobin, and light of a specific wavelength band has peak wavelengths in wavelength bands having different absorption coefficients for oxyhemoglobin and reduced hemoglobin. Is preferred.
  • the specific wavelength band includes wavelength bands of 400 ⁇ 10 nm, 440 ⁇ 10 nm, 470 ⁇ 10 nm, or 600 nm to 750 nm, and light of the specific wavelength band is 400 ⁇ 10 nm, 440 ⁇ 10 nm, 470 ⁇ 10 nm It is preferable to have a peak wavelength in a wavelength band of 600 nm or more and 750 nm or less.
  • the medical image is an in-vivo image obtained by copying the inside of a living body, and the in-vivo image preferably has information of fluorescence emitted from a fluorescent substance in the living body.
  • the fluorescence is preferably obtained by irradiating the living body with excitation light included in a wavelength standby of a peak wavelength of 390 or more and 470 nm or less.
  • the medical image is an in-vivo image obtained by copying the inside of a living body, and the specific wavelength band is preferably a wavelength band of infrared light.
  • the specific wavelength band includes a wavelength band of 790 nm to 820 nm, or 905 nm to 970 nm, and light of a specific wavelength band has a peak wavelength in a wavelength band of 790 nm to 820 nm, or 905 nm to 970 nm. Is preferred.
  • the medical image is a special light image obtained based on a normal light image obtained by irradiating light of a plurality of wavelength bands as light of a white band or light of a white band and having a signal of a specific wavelength band. Is preferred. It is preferable that the signal in the specific wavelength band is obtained by calculation based on RGB or CMY color information included in the normal light image.
  • Medical images are a normal light image obtained by irradiating light of a plurality of wavelength bands as light of a white band or light of a white band, and a special light image obtained by irradiating light of a specific wavelength band. It is preferable that it is a calculation image obtained by calculation based on at least one.
  • the endoscope system of the present invention includes an endoscope, an image acquisition unit, an attention area detection unit, a display unit, a sight line detection unit, and an attention area selection unit.
  • the endoscope images an observation target.
  • the image acquisition unit acquires a medical image obtained by imaging an observation target with an endoscope.
  • the attention area detection unit performs an area detection process of detecting the attention area from the medical image.
  • the line-of-sight detection unit detects a line-of-sight point indicating a position at which the line of sight directed by the user to the display unit intersects the display unit.
  • the region-of-interest selection unit selects a first region of interest including a gaze point from among the plurality of regions of interest.
  • a diagnosis support apparatus includes the medical image processing system according to the present invention described above.
  • the medical service support device of the present invention includes the medical image processing system of the present invention described above.
  • the user operating the endoscope can directly make a determination on each region of interest.
  • FIG. 6 is an explanatory view showing a region selection process and a region determination process. It is an explanatory view showing data generation processing for study. It is an explanatory view showing learning processing. It is a flowchart which shows a series of flows which perform selection of the 1st attention area which is a suitable area
  • the endoscope system 10 includes an endoscope 12, a light source device 14, a processor device 16, a monitor 18, and a user interface 19.
  • the endoscope 12 emits illumination light to an object to be observed, and captures an image of the object illuminated by the illumination light.
  • the light source device 14 generates illumination light for irradiating a subject.
  • the processor device 16 performs system control, image processing, and the like of the endoscope system 10.
  • the monitor 18 is a display unit that displays an image output from the processor device 16.
  • the user interface 19 is an input device for performing setting input and the like to the processor device 16 and the like, and includes a keyboard KB, a mouse MS, and the like.
  • the user interface 19 is not limited to the mouse MS and the keyboard KB, and may be a graphical user interface, voice input, a touch display, or the like.
  • the endoscope 12 includes an insertion portion 12a to be inserted into a subject, an operation portion 12b provided at a proximal end portion of the insertion portion 12a, a curved portion 12c provided at the distal end side of the insertion portion 12a, and a distal end portion 12d. ,have.
  • the bending portion 12c is bent by operating the angle knob 12e of the operation portion 12b.
  • the bending of the bending portion 12 c causes the tip 12 d to face in a desired direction.
  • the tip end 12d is provided with an injection port (not shown) for injecting air, water or the like toward the subject.
  • the operation unit 12b is provided with a zoom operation unit 13a.
  • a forceps channel (not shown) for inserting a treatment tool or the like is provided from the insertion portion 12a to the distal end portion 12d. The treatment tool is inserted into the forceps channel from the forceps inlet 12f.
  • the light source device 14 includes a light source unit 20 and a light source control unit 22.
  • the light source unit 20 emits illumination light for illuminating a subject.
  • the light source unit 20 includes one or more light sources.
  • the light source control unit 22 controls the drive of the light source unit 20.
  • the light source control unit 22 independently controls the timing of turning on or off the light source constituting the light source unit 20, the light emission amount at the time of lighting, and the like. As a result, the light source unit 20 can emit plural types of illumination lights having different light emission amounts and light emission timings.
  • the illumination light emitted by the light source unit 20 is incident on the light guide 41.
  • the light guide 41 is incorporated in the endoscope 12 and the universal cord (not shown), and propagates the illumination light to the distal end 12 d of the endoscope 12.
  • the universal cord is a cord that connects the endoscope 12 to the light source device 14 and the processor device 16.
  • a multimode fiber can be used. As an example, it is possible to use a thin fiber cable having a core diameter of 105 ⁇ m, a cladding diameter of 125 ⁇ m, and a diameter of ⁇ 0.3 to 0.5 mm including a protective layer to be an outer shell.
  • An illumination optical system 30 a and an imaging optical system 30 b are provided at the distal end 12 d of the endoscope 12.
  • the illumination optical system 30 a has an illumination lens 45, and illumination light is emitted toward the subject through the illumination lens 45.
  • the imaging optical system 30 b includes an objective lens 46, a zoom lens 47, and an image sensor 48.
  • the image sensor 48 is a reflected light of illumination light returning from the subject via the objective lens 46 and the zoom lens 47 (in addition to the reflected light, the scattered light, the fluorescence emitted from the subject, or the drug administered to the subject)
  • the subject is imaged using fluorescence and the like.
  • the zoom lens 47 is moved by operating the zoom operation unit 13 a, and the image sensor 48 is used to magnify or reduce the subject to be imaged.
  • the image sensor 48 is, for example, a color sensor having a primary color filter, and has B pixels (blue pixels) having blue color filters, G pixels (green pixels) having green color filters, and R having red color filters. There are three types of pixels (red pixels). Blue color filters transmit mainly violet to blue light. The green color filter is mainly green light. The red color filter transmits mainly red light. As described above, when an object is imaged using the primary color image sensor 48, at most, a B image (blue image) obtained from B pixels, a G image (green image) obtained from G pixels, and an R obtained from R pixels Three types of images (red image) can be obtained simultaneously.
  • a charge coupled device (CCD) sensor or a complementary metal oxide semiconductor (CMOS) sensor can be used.
  • CMOS complementary metal oxide semiconductor
  • the complementary color sensor includes, for example, a cyan pixel provided with a cyan color filter, a magenta pixel provided with a magenta color filter, a yellow pixel provided with a yellow color filter, and a green pixel provided with a green color filter.
  • the image obtained from the pixels of each color when using a complementary color sensor can be converted into a B image, a G image, and an R image by performing complementary-primary color conversion.
  • a monochrome sensor without a color filter can be used as the image sensor 48. In this case, an image of each color can be obtained by sequentially imaging the subject using illumination light of each color such as BGR.
  • the processor device 16 includes a central control unit 52, an image acquisition unit 54, an image processing unit 61, and a display control unit 66.
  • the central control unit 52 performs overall control of the endoscope system 10 such as synchronous control of the irradiation timing of the illumination light and the imaging timing.
  • the central control unit 52 controls the input various settings as the light source control unit 22, the image sensor 48, or the image processing unit 61.
  • the data is input to each part of the endoscope system 10.
  • the image acquisition unit 54 acquires, from the image sensor 48, an image obtained by imaging a subject.
  • the image acquired by the image acquisition unit 54 is an image acquired by a medical device such as the endoscope 12 and thus is referred to as a medical image.
  • the image acquisition unit 54 includes a DSP (Digital Signal Processor) 56, a noise reduction unit 58, and a conversion unit 59, and uses these to perform various processes on the acquired medical image as needed.
  • the DSP 56 performs various processing such as defect correction processing, offset processing, gain correction processing, linear matrix processing, gamma conversion processing, demosaicing processing, and YC conversion processing, as necessary, on the acquired medical image.
  • the defect correction process is a process of correcting the pixel value of the pixel corresponding to the defective pixel of the image sensor 48.
  • the offset process is a process of reducing the dark current component from the image subjected to the defect correction process and setting an accurate zero level.
  • the gain correction process is a process of adjusting the signal level of each image by multiplying the image subjected to the offset process by the gain.
  • the linear matrix processing is processing for improving the color reproducibility of the image subjected to the offset processing, and the gamma conversion processing is processing for adjusting the brightness and saturation of the image after the linear matrix processing.
  • demosaicing processing is processing for interpolating the pixel value of a missing pixel, and is applied to an image after gamma conversion processing.
  • the missing pixels are pixels having no pixel value due to the arrangement of the color filters (because pixels of other colors are arranged in the image sensor 48).
  • the demosaicing process interpolates the B image to generate pixel values of pixels located at G and R pixel positions of the image sensor 48.
  • the YC conversion process is a process of converting the image after the demosaicing process into a luminance channel Y, a color difference channel Cb, and a color difference channel Cr.
  • the noise reduction unit 58 performs noise reduction processing on the luminance channel Y, the color difference channel Cb, and the color difference channel Cr using, for example, a moving average method or a median filter method.
  • the conversion unit 59 reconverts the luminance channel Y, the color difference channel Cb, and the color difference channel Cr after the noise reduction processing into an image of each color of BGR.
  • the image processing unit 61 performs various types of image processing on the medical image acquired by the image acquisition unit 54. Further, the image processing unit 61 detects an attention area from the medical image, and calculates diagnosis support information for supporting diagnosis of the observation target from the detected attention area. The detection of the area of interest and the calculation of the diagnosis support information will be described later.
  • the display control unit 66 converts the medical image or the diagnosis support information sent from the image processing unit 61 into a format suitable for display on the monitor 18 and outputs the converted format to the monitor 18. As a result, at least the medical image and the diagnostic support information are displayed on the monitor 18.
  • the image processing unit 61 includes an attention area detection unit 70, a diagnosis support information calculation unit 72, a gaze image generation unit 74, an image synthesis unit 76, an attention area selection unit 78, and an observation time.
  • a measurement unit 79, an area determination unit 80, and a learning data generation unit 82 are provided.
  • the attention area detection unit 70 performs an area detection process of detecting an attention area to be noted as a target of examination or diagnosis from a medical image.
  • the attention area detection unit 70 is configured of, for example, a CNN (Convolutional Neural Network) or Adaboost using pixel gradient features. Therefore, the attention area detection unit 70 can perform learning processing for increasing the detection accuracy of the attention area in addition to the area detection processing. Whether the region detection process or the learning process is to be performed is determined by the operation of the user interface 19.
  • the region of interest detection unit 70 detects the region of interest from the input medical image, and the region including the region of interest is detected. Output the detected image.
  • a rectangular region of interest ROI that surrounds the periphery of the lesion is displayed.
  • the shape of the region of interest ROI is represented by a square (rectangle) in FIG. 5, the shape other than the rectangle may be represented by, for example, a circle, an ellipse, or the like.
  • the learning process of the attention area detection unit 70 will be described later.
  • the diagnosis support information calculation unit 72 calculates various index values from the attention area detected by the attention area detection unit 70, and calculates diagnosis support information for supporting diagnosis of a lesion based on the calculated various index values.
  • the various index values include blood vessel index values related to blood vessels such as blood vessel density and blood vessel travel patterns, and ductal index values related to duct structure.
  • the diagnosis support information may include, for example, the degree of progression (stage) of the lesion. As shown in FIG. 5, the calculated diagnosis support information 84 is displayed on the monitor 18 in association with the region of interest ROI together with the region detection image (“Stage 1” in FIG. 5).
  • the line-of-sight image generation unit 74 generates a line-of-sight image displaying a line-of-sight point EP representing a position where the line of sight directed to the monitor 18 intersects the monitor 18.
  • Information on the line-of-sight point is generated based on the line-of-sight data from the line-of-sight detection unit 75 provided on the front of the monitor 18.
  • An EP (TN) is displayed, and the sight line points EP (T1) to EP (TN) are connected by a connecting line CL so that the locus of the sight line can be seen.
  • the gaze point after a certain time interval is deleted from the gaze image, and instead, the latest gaze point is displayed.
  • the portion of the monitor 18 where the line of sight of the user intersects includes, in addition to the entire screen of the monitor 18, at least a portion where image information is displayed, such as a window in the screen.
  • the image combining unit 76 combines the area detection image and the line-of-sight image to generate a combined image.
  • the positional relationship between the attention area in the area detection image and the gaze point EP currently gazed by the user can be understood. For example, as shown in FIG. 7, when three regions of interest ROIx, ROIy, and ROIz are displayed, the gaze point EP displayed within a certain time interval is concentrated on the region of interest ROIx. From this, it can be understood that the area the user is gazing at is ROIx.
  • the attention area selection unit 78 performs an area selection process of selecting a first attention area including the gaze point EP from among a plurality of attention areas.
  • the region selection process is performed based on the user's instruction regarding the selection of the region of interest.
  • the endoscope 12 The region selection button 13b (region selection operation unit) provided in the operation unit 12b is operated.
  • the attention area selection unit 78 executes an area selection process. By execution of this area selection processing, as shown in FIG.
  • the attention area ROIx in which the line-of-sight point EP is included is selected as the first attention area at the timing when the area selection button 13b is operated (in FIG. 8, 1 ROI x selected as a region of interest is indicated by a double line.
  • the doctor operating the endoscope 12 is correctly detected as the area to be focused without the support of the staff. You will be able to select the areas of interest that you think are present.
  • the area selection button 13b is used as the area selection operation unit, other than that, a foot switch FS (see FIG. 1), voice recognition using a microphone or the like can also be used.
  • the observation time measurement unit 79 measures the time during which the sight point EP is in the attention area as the observation time, and then the attention area selection unit 78 measures it with the observation time measurement unit 79. An attention area whose observation time exceeds the specific observation time may be selected as the first attention area.
  • the area determination unit 80 determines that the first area of interest is an appropriate area correctly detected as the area of interest.
  • An area determination process is performed on the second attention area other than the attention area to determine that it is an erroneously detected area that is erroneously detected as the attention area.
  • a correct / incorrected judged image including information on an appropriate area and an erroneously detected area is obtained.
  • the attention area ROIx selected as the first attention area is determined to be an appropriate area
  • attention areas ROIy and ROIz which are second attention areas not selected as the first attention area are It is determined as a false detection area.
  • the learning data generation unit 82 associates the medical image input to the attention area detection unit 70 with the correct / incorrect determination image obtained by the area judgment unit 80 to obtain the attention area detection unit 70.
  • a learning data generation process is performed to generate learning data for learning.
  • the generated learning data is stored in the learning data storage unit 82a, and is used when the attention area detection unit 70 performs the learning process.
  • the attention area detection unit 70 reads the learning data from the learning data storage unit 82a, and the accuracy of the area detection process based on the read learning data.
  • the learning processing is performed on the attention area detection unit 70, and is performed on another specific processing unit 83 different from the attention area detection unit 70, and the learning processing specific processing unit It may be replaced with 70.
  • the specified processing unit after the replacement functions the attention area detection unit 70.
  • the attention area detection unit 70 detects an attention area from the medical image in response to the input of the medical image, and outputs an area detection image including the detected attention area.
  • the output area detection image is superimposed on the medical image and displayed on the monitor 18.
  • the user's gaze is detected by the gaze detection unit 75.
  • a line-of-sight image is obtained in which a line-of-sight point representing a line of sight directed by the user to the monitor 18 a predetermined time ago is displayed.
  • the line-of-sight image is synthesized with the area detection image, and the synthesized image obtained by this synthesis is displayed on the monitor 18.
  • the area selection button 13 b is selected. Manipulate At the timing when the region selection button 13b is operated, the region of interest ROIx in which the gaze point EP is included is selected as a first region of interest.
  • the first attention area After selecting the first attention area, it is determined that the first attention area is an appropriate area correctly detected as the attention area, and the second attention area other than the first attention area is determined as the attention area
  • An area determination process is performed to determine that the area is an erroneously detected area detected erroneously.
  • a correct / incorrected judged image including information on an appropriate area and an erroneously detected area is obtained.
  • Learning data is generated by mutually associating the correctness-corrected image and the medical image input to the attention area detection unit 70.
  • the blood vessel index value calculated by the diagnosis support information calculation unit 72 for example, the blood vessel density, the blood vessel thickness, and the blood vessel index value, the number of blood vessels, the number of branches, the branch angle, the branch point Distance, crossing number, thickness change, interval, depth based on mucous membrane, height difference, inclination, contrast, color, color change, meandering degree, blood concentration, oxygen saturation, arterial percentage, vein There are proportions, concentrations of dyes administered, running patterns, and blood flow.
  • the blood vessel density is represented by the proportion of blood vessels contained in a specific area in the image.
  • the thickness of the blood vessel (blood vessel diameter) is the distance between the boundary line of the blood vessel and the mucous membrane, and for example, counts the number of pixels along the lateral direction of the blood vessel from the edge of the detected blood vessel through the blood vessel. Count by. Therefore, although the thickness of the blood vessel is the number of pixels, it can be converted to a unit of length such as " ⁇ m" if necessary when the imaging distance and zoom magnification etc. at the time of imaging a medical image are known. is there.
  • the number of blood vessels is the number of blood vessels detected in the entire medical image or in the region of interest.
  • the number of blood vessels is calculated using, for example, the number of branch points of the detected blood vessels (number of branches), the number of intersections with other blood vessels (number of intersections), and the like.
  • the bifurcation angle of a blood vessel is an angle which two blood vessels make at a bifurcation point.
  • the distance between bifurcation points is a linear distance between any bifurcation point and its neighboring bifurcation point, or a length along a blood vessel from any bifurcation point to its neighboring bifurcation point.
  • the number of crossings of blood vessels is the number of crossing points where blood vessels having different submucosal depths cross on a medical image. More specifically, the number of crossings of blood vessels is the number of blood vessels at relatively shallow positions under the submucosa crossing blood vessels at deep positions.
  • the change in the thickness of the blood vessel is blood vessel information related to the variation in the thickness of the blood vessel, and is also referred to as the aperture unequal degree.
  • the change in thickness of the blood vessel is, for example, the rate of change in the diameter of the blood vessel (also referred to as the degree of dilation).
  • the medical image acquired in the past examination With respect to the detected blood vessel thickness, a temporal change in the same blood vessel thickness detected from a medical image obtained in a subsequent new examination may be used as a change in blood vessel thickness.
  • the ratio of the small diameter portion or the ratio of the large diameter portion may be calculated.
  • the thin diameter portion is a portion whose thickness is equal to or less than the threshold
  • the large diameter portion is a portion whose thickness is thicker than the threshold.
  • the complexity of change in blood vessel thickness (hereinafter referred to as “complexity of change in thickness”) is blood vessel information that indicates how complex the change is in the case of blood vessel thickness change.
  • the blood vessel information is calculated by combining a plurality of blood vessel information representing a change in the thickness of the blood vessel (that is, the change rate of the blood vessel diameter, the ratio of the narrow diameter portion, or the ratio of the wide diameter portion).
  • the complexity of the thickness change can be determined, for example, by the product of the change rate of the blood vessel diameter and the ratio of the small diameter portion.
  • the length of the blood vessel is the number of pixels counted along the longitudinal direction of the detected blood vessel.
  • the distance between blood vessels is the number of pixels of pixels representing the mucous membrane between the edges of the detected blood vessels.
  • the blood vessel interval has no value.
  • the blood vessel depth is measured relative to the mucous membrane (more specifically, the surface of the mucous membrane).
  • the depth of the blood vessel relative to the mucous membrane can be calculated, for example, based on the color of the blood vessel.
  • blood vessels located near the surface of the mucous membrane are expressed in magenta
  • blood vessels located far from the mucous membrane surface and deep in the submucosa are expressed in cyan.
  • the depth of the blood vessel is calculated for each pixel based on the mucous membrane on the basis of the balance of the R, G and B color signals of the detected pixel.
  • the height difference of the blood vessel is the size of the difference in the depth of the blood vessel.
  • the height difference of one blood vessel to be noticed is obtained by the difference between the depth (maximum depth) of the deepest part of the blood vessel and the depth (minimum depth) of the shallowest part. When the depth is constant, the height difference is zero.
  • the blood vessel may be divided into a plurality of sections, and the inclination of the blood vessel may be calculated in each section.
  • the area of the blood vessel is a value proportional to the number of pixels of a pixel detected as a blood vessel or the number of pixels of a pixel detected as a blood vessel.
  • the area of the blood vessel is calculated within the region of interest, outside the region of interest, or for the entire medical image.
  • the contrast of the blood vessel is the relative contrast to the mucous membrane to be observed.
  • the contrast of the blood vessel is calculated, for example, by “Y V / Y M ” or “(Y V ⁇ Y M ) / (Y V + Y M )” using the blood vessel brightness Y V and the mucous membrane brightness Y M Do.
  • the color of a blood vessel is each value of RGB of the pixel showing a blood vessel.
  • the change in blood vessel color is the difference or ratio between the maximum value and the minimum value of each of the RGB values of the pixel representing the blood vessel.
  • the ratio of the maximum value to the minimum value of the pixel value of the B pixel representing the blood vessel, the ratio of the maximum value to the minimum value of the pixel value of the G pixel, or the ratio of the maximum value to the minimum value of the pixel value of the R pixel is Represents the change in color of
  • the color change of the blood vessel and the color of the blood vessel may be calculated for each value such as cyan, magenta, yellow, and green by converting into a complementary color.
  • the meandering degree of a blood vessel is blood vessel information that represents the width of a range in which the blood vessel travels in a meandering manner.
  • the meandering degree of the blood vessel is, for example, the smallest rectangular area (number of pixels) including the blood vessel for which the meandering degree is calculated. Further, the ratio of the length of the blood vessel to the straight distance between the start point and the end point of the blood vessel may be the meander degree of the blood vessel.
  • the blood concentration of a blood vessel is blood vessel information that is proportional to the amount of hemoglobin contained in the blood vessel. Since the ratio (G / R) of the pixel value of the G pixel to the pixel value of the R pixel representing the blood vessel is proportional to the amount of hemoglobin, the blood concentration is calculated for each pixel by calculating the value of G / R. Can.
  • Blood vessel oxygen saturation is the amount of oxygenated hemoglobin relative to the total amount of hemoglobin (total amount of oxygenated hemoglobin and reduced hemoglobin).
  • the oxygen saturation may be calculated using a medical image obtained by photographing an observation target with light of a specific wavelength band (for example, blue light with a wavelength of about 470 ⁇ 10 nm) having a large difference between the absorption coefficients of oxidized hemoglobin and reduced hemoglobin. it can.
  • a specific wavelength band for example, blue light with a wavelength of about 470 ⁇ 10 nm
  • the pixel value of the B pixel representing the blood vessel has a correlation with the oxygen saturation, so using a table or the like that corresponds the pixel value of the B pixel to oxygen saturation,
  • the oxygen saturation of each pixel to be represented can be calculated.
  • the proportion of arteries is the ratio of the number of pixels of arteries to the number of pixels of all blood vessels.
  • the ratio of veins is the ratio of the number of pixels of veins to the number of pixels of all blood vessels.
  • Arteries and veins can be distinguished by oxygen saturation. For example, if a blood vessel having an oxygen saturation of 70% or more is an artery and a blood vessel having an oxygen saturation of less than 70% is a vein, the detected blood vessels can be divided into an artery and a vein. Can be calculated.
  • the concentration of the administered dye is the concentration of the dye dispersed to the observation subject or the concentration of the dye injected into the blood vessel by intravenous injection.
  • the concentration of the administered dye is calculated, for example, by the ratio of the pixel value of the dye color to the pixel value of the pixel other than the dye color. For example, when a pigment colored in blue is administered, the ratio B / G of the B image to the G image, the ratio B / R of the B image to the R image, etc. are fixed (or temporarily attached) to the observation target Represents the concentration of dye.
  • the travel pattern of the blood vessel is blood vessel information regarding the travel direction of the blood vessel.
  • the traveling pattern of the blood vessel is, for example, an average angle (traveling direction) of the blood vessel with respect to a reference line set arbitrarily, dispersion of an angle formed by the blood vessel with respect to the reference line arbitrarily set (variation in traveling direction), and the like.
  • Blood flow in blood vessels is the number of red blood cells per unit time.
  • the Doppler shift frequency of each pixel representing a blood vessel of a medical image is calculated using a signal obtained by the ultrasound probe. You can determine the flow rate.
  • the present invention is applied to an endoscope system for processing an endoscopic image which is one of medical images, but medical images other than endoscopic images are processed.
  • the present invention is also applicable to medical image processing systems.
  • the present invention is also applicable to a diagnosis support apparatus for performing diagnosis support to a user using a medical image.
  • the present invention can be applied to a medical service support apparatus for supporting medical services such as diagnostic reports using medical images.
  • V-LED Volt Light Emitting Diode
  • B-LED Blue Light Emitting Diode
  • G-LED Green Light Emitting Diode
  • the V-LED 20a emits violet light V in a wavelength band of 380 nm to 420 nm.
  • the B-LED 20b emits blue light B in a wavelength band of 420 nm to 500 nm.
  • the wavelength cut filter 23 cuts off at least the wavelength side longer than 450 nm of the peak wavelength.
  • the blue light Bx transmitted through the wavelength cut filter 23 is in the wavelength range of 420 to 460 nm.
  • the reason why light in the wavelength range longer than 460 nm is cut is a factor that reduces the blood vessel contrast of the blood vessel to be observed. It is because there is.
  • the wavelength cut filter 23 may reduce the light in the wavelength range longer than 460 nm instead of cutting the light in the wavelength range longer than 460 nm.
  • the G-LED 20c emits green light G having a wavelength band ranging from 480 nm to 600 nm.
  • the R-LED 20d emits red light R in a wavelength band of 600 nm to 650 nm.
  • the light source device 14 When light in a white band (white light) is emitted, all the V-LED 20a, B-LED 20b, G-LED 20c, and R-LED 20d are turned on. As a result, as shown in FIG. 13, the light source device 14 emits white light including violet light V, blue light Bx, green light G, and red light R. White light is almost white because it has a certain intensity or more from the blue band to the red band. In the case of emitting specific light having a peak wavelength in a wavelength band of 440 ⁇ 10 nm as light of a specific wavelength band (specific light), for example, as shown in FIG. , And green light G and red light R are emitted for specific light which is larger than the amount of light emission.
  • the illumination light may be emitted using a laser light source and a phosphor.
  • a blue laser light source (denoted as “445 LD", where LD represents “Laser Diode”) 104 which emits blue laser light with a peak wavelength of 445 ⁇ 10 nm, as shown in FIG.
  • a blue-violet laser light source (denoted as "405 LD") 106 which emits blue-violet laser light having a peak wavelength of 405 ⁇ 10 nm.
  • the illumination optical system 30a is provided with a phosphor 110 to which blue laser light or blue-violet laser light from the light guide 24 is incident.
  • the phosphor 110 is excited by blue laser light to emit fluorescence.
  • part of the blue laser light transmits without exciting the phosphor 110.
  • the blue-violet laser light transmits without exciting the phosphor 110.
  • the light emitted from the phosphor 110 illuminates the body to be observed through the illumination lens 32.
  • the blue laser light source 104 is turned on, and mainly the blue laser light is incident on the phosphor 110, so that blue laser light and blue laser light as shown in FIG. 16 are used.
  • White light is generated by combining the fluorescence emitted from the phosphor 110.
  • specific light having a peak wavelength in the wavelength band of 440 ⁇ 10 nm as light of a specific wavelength band (specific light)
  • the blue laser light source 104 and the blue violet laser light source 106 are turned on. Both the purple laser light and the blue laser light are incident on the phosphor 110.
  • the specific light which combined the fluorescence which carried out the excitation light emission from the fluorescent substance 110 by blue-violet laser light, blue laser light, and blue laser light is emitted.
  • the half width of the blue laser light or the blue-violet laser light is preferably about ⁇ 10 nm.
  • a broad area type InGaN-based laser diode can be used, and an InGaNAs-based laser diode or a GaNAs-based laser diode can also be used.
  • a light emitter such as a light emitting diode may be used as the light source.
  • the phosphor 110 absorbs a part of blue laser light and emits plural colors of green to yellow (for example, a YAG phosphor or a phosphor such as BAM (BaMgAl 10 O 17 )). It is preferable to use what is comprised including.
  • a YAG phosphor or a phosphor such as BAM (BaMgAl 10 O 17 ) for example, a YAG phosphor or a phosphor such as BAM (BaMgAl 10 O 17 )
  • BAM BaMgAl 10 O 17
  • the illumination light may be emitted using a broadband light source such as a xenon lamp and a rotary filter.
  • the light source unit 20 is provided with a broadband light source 202, a rotation filter 204, and a filter switching unit 206.
  • a diaphragm 203 is provided between the broadband light source 202 and the rotary filter 204.
  • the diaphragm control unit 205 adjusts the area of the opening of the diaphragm 203.
  • the aperture control unit 205 controls the aperture 203 based on the light control signal from the processor device 16.
  • the broadband light source 202 is a xenon lamp, a white LED, or the like, and emits broadband light ranging in wavelength from blue to red.
  • the rotary filter 204 includes a white light filter 210 provided on the inner side closest to the rotation axis, and a specific light filter 212 provided on the outer side of the white light filter 210 (see FIG. 19).
  • the filter switching unit 206 moves the rotary filter 204 in the radial direction. Specifically, when the white light is emitted, the filter switching unit 206 inserts the white light filter 210 into the optical path of the broadband light. When the light (specific light) in a specific wavelength band is emitted, the filter switching unit 206 inserts the filter 212 for specific light into the optical path of the broadband light.
  • the white light filter 210 is provided with a B filter 210 a, a G filter 210 b, and an R filter 210 c along the circumferential direction.
  • the B filter 210a transmits wide band blue light B having a wavelength range of 400 to 500 nm out of the wide band light.
  • the G filter 210 b transmits green light G of the broadband light.
  • the R filter 210c transmits the red light R of the broadband light. Therefore, in the case of emitting white light, blue light B, green light G, and red light R are sequentially emitted as white light by rotating the rotary filter 204.
  • the filter for specific light 212 is provided with a Bn filter 212a and a G filter 212b along the circumferential direction.
  • the Bn filter 212a transmits blue narrow band light Bn of 400 to 450 nm out of wide band light.
  • the G filter 212 b transmits green light G out of the wide band light. Therefore, when the specific light is emitted, the blue narrow band light Bn and the green light G are sequentially irradiated toward the observation target as the specific light by rotating the rotary filter 204.
  • each time the observation target is illuminated with blue light B, green light G, red light R, monochrome The image sensor captures an image of the observation target. An image including a component of white light is generated by the B image, the G image, and the R image obtained by imaging the observation target.
  • the observation object is imaged by a monochrome image sensor, and the Bn image and G image obtained by this imaging.
  • the present invention is applied to an endoscope system for processing an endoscopic image which is one of medical images, but medical images other than endoscopic images are processed.
  • the present invention is also applicable to medical image processing systems.
  • the present invention is also applicable to a diagnosis support apparatus for performing diagnosis support to a user using a medical image.
  • the present invention can be applied to a medical service support apparatus for supporting medical services such as diagnostic reports using medical images.
  • the diagnosis support apparatus 600 is used in combination with a modality such as a medical image processing system 602 or a Picture Archiving and Communication Systems (PACS) 604.
  • a modality such as a medical image processing system 602 or a Picture Archiving and Communication Systems (PACS) 604.
  • the medical service support apparatus 610 includes various inspection apparatuses such as a first medical image processing system 621, a second medical image processing system 622,. Connect via 626.
  • the medical service support device 610 receives medical images from the first to Nth medical image processing systems 621, 622, ..., 623, and supports medical services based on the received medical images.
  • the attention area detection unit 70 the diagnosis support information calculation unit 72, the gaze image generation unit 74, the image synthesis unit 76, the attention area selection unit 78, the observation time measurement unit 79, and the area determination
  • the hardware-like structure of the processing unit (processing unit) that executes various processes such as the unit 80, the learning data generation unit 82, the learning data storage unit 82a, or the specific processing unit 83 is various as shown below. It is a processor.
  • CPU Central Processing Unit
  • FPGA Field Programmable Gate Array
  • PLD Programmable logic device
  • One processing unit may be configured by one of these various types of processors, or a combination of two or more processors of the same or different types (for example, a plurality of FPGAs, a combination of a CPU and an FPGA, a CPU and (A combination of GPUs).
  • a plurality of processing units may be configured by one processor.
  • one processor is configured by a combination of one or more CPUs and software as represented by computers such as clients and servers; There is a form in which this processor functions as a plurality of processing units.
  • SoC system on chip
  • IC integrated circuit
  • circuitry in the form in which circuit elements such as semiconductor elements are combined.

Landscapes

  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Surgery (AREA)
  • Optics & Photonics (AREA)
  • Biomedical Technology (AREA)
  • Medical Informatics (AREA)
  • Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
  • Pathology (AREA)
  • Radiology & Medical Imaging (AREA)
  • Astronomy & Astrophysics (AREA)
  • Biophysics (AREA)
  • Engineering & Computer Science (AREA)
  • Heart & Thoracic Surgery (AREA)
  • General Physics & Mathematics (AREA)
  • Molecular Biology (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Endoscopes (AREA)

Abstract

L'invention concerne un système de traitement d'image médicale, un système d'endoscope, un dispositif d'aide au diagnostic et un dispositif d'aide à la pratique médicale, un utilisateur actionnant un endoscope pouvant effectuer une détermination directement pour chaque région d'intérêt lorsqu'une pluralité de régions d'intérêt sont détectées. Dans la présente invention, une région d'intérêt est détectée à partir d'une image médicale. Un moniteur (18) affiche la région d'intérêt dans l'image médicale. Une unité de détection de ligne de visée (75) détecte un point de ligne de visée représentant la position à laquelle la ligne de visée d'un utilisateur faisant face au moniteur coupe le moniteur. Une unité de sélection de région d'intérêt (78) sélectionne une première région d'intérêt dans laquelle le point de ligne de visée est inclus parmi une pluralité de régions d'intérêt.
PCT/JP2018/039771 2017-10-26 2018-10-25 Système de traitement d'image médicale, système d'endoscope, dispositif d'aide au diagnostic, et dispositif d'aide à la pratique médicale Ceased WO2019082993A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
JP2019550301A JP6850358B2 (ja) 2017-10-26 2018-10-25 医療画像処理システム、内視鏡システム、診断支援装置、及び医療業務支援装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
JP2017-207059 2017-10-26
JP2017207059 2017-10-26

Publications (1)

Publication Number Publication Date
WO2019082993A1 true WO2019082993A1 (fr) 2019-05-02

Family

ID=66247481

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/JP2018/039771 Ceased WO2019082993A1 (fr) 2017-10-26 2018-10-25 Système de traitement d'image médicale, système d'endoscope, dispositif d'aide au diagnostic, et dispositif d'aide à la pratique médicale

Country Status (2)

Country Link
JP (1) JP6850358B2 (fr)
WO (1) WO2019082993A1 (fr)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2021029293A1 (fr) * 2019-08-13 2021-02-18
CN115066196A (zh) * 2020-02-06 2022-09-16 富士胶片株式会社 医用图像处理装置、内窥镜系统、医用图像处理方法及程序
CN115361898A (zh) * 2020-04-03 2022-11-18 富士胶片株式会社 医疗图像处理装置、内窥镜系统及医疗图像处理装置的工作方法、以及医疗图像处理装置用程序

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012249804A (ja) * 2011-06-02 2012-12-20 Olympus Corp 蛍光観察装置
JP2015100479A (ja) * 2013-11-22 2015-06-04 日立アロカメディカル株式会社 超音波画像処理装置
JP2015136397A (ja) * 2014-01-20 2015-07-30 富士フイルム株式会社 内視鏡システム用プロセッサ装置、内視鏡システム、内視鏡システム用プロセッサ装置の作動方法、内視鏡システムの作動方法
JP2016067778A (ja) * 2014-09-30 2016-05-09 富士フイルム株式会社 内視鏡システム、プロセッサ装置、内視鏡システムの作動方法、及びプロセッサ装置の作動方法
WO2017038241A1 (fr) * 2015-08-28 2017-03-09 富士フイルム株式会社 Dispositif d'opération avec un instrument, procédé d'opération avec un instrument, et système d'instrument électronique

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2012249804A (ja) * 2011-06-02 2012-12-20 Olympus Corp 蛍光観察装置
JP2015100479A (ja) * 2013-11-22 2015-06-04 日立アロカメディカル株式会社 超音波画像処理装置
JP2015136397A (ja) * 2014-01-20 2015-07-30 富士フイルム株式会社 内視鏡システム用プロセッサ装置、内視鏡システム、内視鏡システム用プロセッサ装置の作動方法、内視鏡システムの作動方法
JP2016067778A (ja) * 2014-09-30 2016-05-09 富士フイルム株式会社 内視鏡システム、プロセッサ装置、内視鏡システムの作動方法、及びプロセッサ装置の作動方法
WO2017038241A1 (fr) * 2015-08-28 2017-03-09 富士フイルム株式会社 Dispositif d'opération avec un instrument, procédé d'opération avec un instrument, et système d'instrument électronique

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPWO2021029293A1 (fr) * 2019-08-13 2021-02-18
WO2021029293A1 (fr) * 2019-08-13 2021-02-18 富士フイルム株式会社 Dispositif de traitement d'images médicales, système d'endoscope et procédé de traitement d'images médicales
US12232689B2 (en) 2019-08-13 2025-02-25 Fujifilm Corporation Medical image processing apparatus, endoscope system, and medical image processing method
CN115066196A (zh) * 2020-02-06 2022-09-16 富士胶片株式会社 医用图像处理装置、内窥镜系统、医用图像处理方法及程序
US12373973B2 (en) 2020-02-06 2025-07-29 Fujifilm Corporation Medical image processing apparatus, endoscope system, medical image processing method, and program
CN115361898A (zh) * 2020-04-03 2022-11-18 富士胶片株式会社 医疗图像处理装置、内窥镜系统及医疗图像处理装置的工作方法、以及医疗图像处理装置用程序

Also Published As

Publication number Publication date
JPWO2019082993A1 (ja) 2020-11-12
JP6850358B2 (ja) 2021-03-31

Similar Documents

Publication Publication Date Title
US11426054B2 (en) Medical image processing system, endoscope system, diagnosis support apparatus, and medical service support apparatus
JP6785941B2 (ja) 内視鏡システム及びその作動方法
JP6785948B2 (ja) 医療用画像処理装置及び内視鏡システム並びに医療用画像処理装置の作動方法
JP6488249B2 (ja) 血管情報取得装置、内視鏡システム及び血管情報取得方法
US10231658B2 (en) Endoscope system, processor device for endoscope system, operation method for endoscope system, and operation method for processor device
US12082769B2 (en) Endoscope system
JP7670797B2 (ja) 画像処理装置及び内視鏡システム並びに画像処理プログラム
JP6538634B2 (ja) プロセッサ装置及び内視鏡システム並びにプロセッサ装置の作動方法
JP6924837B2 (ja) 医療画像処理システム、内視鏡システム、診断支援装置、並びに医療業務支援装置
JP6796725B2 (ja) 医療画像処理システム、内視鏡システム、診断支援装置、及び医療業務支援装置
JP7059297B2 (ja) 医療画像処理装置
WO2019012911A1 (fr) Dispositif de traitement d'image médicale, système d'endoscope, dispositif d'aide au diagnostic, et dispositif d'aide à une intervention médicale
JP6763025B2 (ja) プロセッサ装置及びプロセッサ装置の作動方法
US11064864B2 (en) Processor device, endoscope system, and method of operating processor device
JP6850358B2 (ja) 医療画像処理システム、内視鏡システム、診断支援装置、及び医療業務支援装置
JPWO2018159082A1 (ja) 内視鏡システム、プロセッサ装置、及び、内視鏡システムの作動方法

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18871403

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
ENP Entry into the national phase

Ref document number: 2019550301

Country of ref document: JP

Kind code of ref document: A

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 18871403

Country of ref document: EP

Kind code of ref document: A1